Langfuse

Send Langfuse traces to Respan with OTEL instrumentation.

Instrument before importing Langfuse so the HTTP client is patched.

Overview

Use the Respan Langfuse instrumentor to redirect Langfuse traces to Respan without changing your Langfuse usage. You can keep using @observe and the Langfuse SDK as usual.

Quickstart

Step 1: Get a Respan API key

Create an API key in the Respan dashboard.

Step 2: Install packages

Python

pip install langfuse respan-instrumentation-langfuse

Step 3: Set environment variables

Create a .env or export environment variables:

.env

RESPAN_API_KEY=your-respan-api-key
RESPAN_BASE_URL=https://api.respan.ai/api

LANGFUSE_PUBLIC_KEY=your-langfuse-public-key
LANGFUSE_SECRET_KEY=your-langfuse-secret-key
LANGFUSE_HOST=https://cloud.langfuse.com

Examples

Below are three common Langfuse patterns using the Respan instrumentor.

Basic decorator

Instrument the Langfuse client and use @observe.

Python

import dotenv
dotenv.load_dotenv(".env", override=True)

import os
from respan_instrumentation_langfuse import LangfuseInstrumentor

# Instrument BEFORE importing Langfuse
instrumentor = LangfuseInstrumentor()
instrumentor.instrument(
    api_key=os.environ["RESPAN_API_KEY"],
    endpoint=os.environ["RESPAN_BASE_URL"] + "/v1/traces/ingest",
)

from langfuse import Langfuse, observe

langfuse = Langfuse(
    public_key="pk-lf-...",
    secret_key="sk-lf-...",
    host="https://cloud.langfuse.com",
)

@observe()
def process_query(query: str):
    return f"Response to: {query}"

result = process_query("Hello World")
print(result)

langfuse.flush()

Generation tracing

Mark a function as a generation with @observe(as_type="generation").

Python

import os
from respan_instrumentation_langfuse import LangfuseInstrumentor

os.environ["RESPAN_API_KEY"] = "your-api-key"

instrumentor = LangfuseInstrumentor()
instrumentor.instrument(
    api_key=os.environ["RESPAN_API_KEY"],
)

from langfuse import Langfuse, observe

langfuse = Langfuse(
    public_key="pk-lf-...",
    secret_key="sk-lf-...",
)

@observe(as_type="generation")
def generate_response(prompt: str):
    return f"Generated: {prompt}"

result = generate_response("Write a poem")
print(result)

langfuse.flush()

Nested traces

Create parent-child relationships with nested @observe functions.

Python

import os
from respan_instrumentation_langfuse import LangfuseInstrumentor

os.environ["RESPAN_API_KEY"] = "your-api-key"

instrumentor = LangfuseInstrumentor()
instrumentor.instrument(
    api_key=os.environ["RESPAN_API_KEY"],
)

from langfuse import Langfuse, observe

langfuse = Langfuse(
    public_key="pk-lf-...",
    secret_key="sk-lf-...",
)

@observe()
def subtask(name: str):
    return f"Completed: {name}"

@observe()
def main_workflow(task: str):
    result1 = subtask("step 1")
    result2 = subtask("step 2")
    return f"Workflow done: {task}"

result = main_workflow("Process request")
print(result)

langfuse.flush()